Fandi Gou

Fandi Gou

Shanghai Jiao Tong University

Publications 📖

Accepted

  1. Fandi Gou, Haikuo Du, Chenyu Zhao and Yunze Cai, A Policy-Guided Reinforcement Learning Method for Encirclement Control in Multiobstacle Environment, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), vol. 36, no. 9, pp. 17034-17046, May 2025.
    • See brief work description here.
  2. Fandi Gou, Chenyu Zhao, Haikuo Du and Yunze Cai, Modeling Deception in Multi-Robot Target-Attacker-Defender Game via Deep Reinforcement Learning, in Proc IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Jun 2025.
    • See brief work description here.
  3. Fandi Gou, Haikuo Du and Yunze Cai, A Graph-Based Safe Reinforcement Learning Method for Multi-agent Cooperation, Neural Networks (NN), vol. 199, p. 108693, Feb 2026.
    • See a brief work description here.
  4. Fandi Gou, Chenyu Zhao, Hengyuan Zhao and Yunze Cai, * Primal-Dual based Safe Reinforcement Learning for Multi-Agent Navigation with Graph Information Aggregation*. Submitted to International Federation of Automatic Control World Congress 2026 (IFAC), Apr 2026.
    • See a brief work description here.

Under Review

  1. Fandi Gou, Chenyu Zhao, Hengyuan Zhao and Yunze Cai, Guide Policy Assisted Reinforcement Learning for Multi-agent Tasks under Restricted Communication. Submitted to IEEE Transactions on Neural Networks and Learning Systems (TNNLS), Apr 2025, major revision.
    • See a brief work description here.
  2. Fandi Gou, Hengyuan Zhao, Chen Yan and Yunze Cai, Graph-based Formation Control with Collision Avoidance via Policy-Guided Reinforcement Learning. Submitted to Neurocomputing, Jan 2026, major revision.
    • See a brief work description here.
  3. Hao Zhang, Fandi Gou, Haowen Wu, Hengyuan Zhao and Yunze Cai, Solving Three-Dimensional Target Attacker Defender Game via Deep Reinforcement Learning. Submitted to Chinese Journal of Aeronautics, Mar 2026, major revision.

In Preparation

In a period of steady accumulation. Immersed in the mathematics behind RL, curriculum learning theories in RL, and safety control these days. Putting paper writing on hold for now.